English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Electrical waves in the heart form rotating spiral or scroll waves duringlife-threatening arrhythmias such as atrial or ventricular fibrillation. Thewave dynamics are typically modeled using coupled partial differentialequations, which describe reaction-diffusion dynamics in excitable media. Morerecently, data-driven generative modeling has emerged as an alternative togenerate spatio-temporal patterns in physical and biological systems. Here, weexplore denoising diffusion probabilistic models for the generative modeling ofelectrical wave patterns in cardiac tissue. We trained diffusion models withsimulated electrical wave patterns to be able to generate such wave patterns inunconditional and conditional generation tasks. For instance, we exploredinpainting tasks, such as reconstructing three-dimensional wave dynamics fromsuperficial two-dimensional measurements, and evolving and generatingparameter-specific dynamics. We characterized and compared thediffusion-generated solutions to solutions obtained with biophysical models andfound that diffusion models learn to replicate spiral and scroll waves dynamicsso well that they could serve as an alternative data-driven approach for themodeling of excitation waves in cardiac tissue. For instance, we found that itis possible to initiate ventricular fibrillation (VF) dynamics instantaneouslywithout having to apply pacing protocols in order to induce wavebreak. The VFdynamics can be created in arbitrary ventricular geometries and can be evolvedover time. However, we also found that diffusion models `hallucinate' wavepatterns when given insufficient constraints. Regardless of these limitations,diffusion models are an interesting and powerful tool with many potentialapplications in cardiac arrhythmia research and diagnostics.

Dreaming of Electrical Waves: Generative Modeling of Cardiac Excitation Waves using Diffusion Models